Towards Accurate Heart Disease Diagnosis: An Overview of Machine Learning Approaches

Résumé fourni par la source

cardiovascular diseases, especially heart ailments, pose substantial health challenges globally, often exacerbated by unhealthy lifestyle habits. Recent technological advances in machine learning (ML) have emerged as a beacon of hope, presenting avenues for swift and efficient heart disease detection. Despite the voluminous health data accumulated daily, its vast analytical potential is frequently overlooked, creating a pronounced knowledge disparity. Thus, it becomes imperative to study recent ML approaches for accurate heart diagnosis, which allows to fetch critical insights. In this paper, we discussed a comparative analysis of ML algorithms, datasets for heart diseases, and compared ML algorithms in terms of metrics like precision, recall, F1 and accuracy. We considered the benchmark Cleveland Heart Dataset for analysis. We observed an accuracy of 84% by Artificial Neural Network (ANN), while Support Vector Machine (SVM) has the highest recall of 95%. The presented findings and analysis indicate the efficacy of the analysis in heart prediction using ML in real-world setups.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.